From c6bb76703f2e7d1904417130994e8a8fdb0b6531 Mon Sep 17 00:00:00 2001
From: Vince Jankovics <javince80@gmail.com>
Date: Thu, 23 Nov 2023 14:00:09 +0000
Subject: [PATCH] Fix IDEFICS dtype (#1214)

# What does this PR do?

<!--
Congratulations! You've made it this far! You're not quite done yet
though.

Once merged, your PR is going to appear in the release notes with the
title you set, so make sure it's a great title that fully reflects the
extent of your awesome contribution.

Then, please replace this with a description of the change and which
issue is fixed (if applicable). Please also include relevant motivation
and context. List any dependencies (if any) that are required for this
change.

Once you're done, someone will review your PR shortly (see the section
"Who can review?" below to tag some potential reviewers). They may
suggest changes to make the code even better. If no one reviewed your PR
after a week has passed, don't hesitate to post a new comment
@-mentioning the same persons---sometimes notifications get lost.
-->

<!-- Remove if not applicable -->

This forces the use of `bfloat16` for IDEFICS. The issue is that with
`float16` the 80b model gives garbage output. Let me know if this
solution is not appropriate and I'll adjust accordingly. For the details
see below.

The current behaviour:
```sh
$ curl 127.0.0.1:8080/generate -X POST -d '{"inputs":"What is Deep Learning?","parameters":{"max_new_tokens":20}}' -H 'Content-Type: application/json'
{"generated_text":""}
```

On closer inspection with:
```python
import requests

headers = { "Content-Type": "application/json"}

query = "What is Deep Learning?"
data = {
    "inputs": query,
    "parameters": {
        "max_new_tokens": 10,
        "return_full_text": True,
        "decoder_input_details": True,
        "do_sample": False,
    },
}

api_url = "http://127.0.0.1:8080"
response = requests.post(api_url + "/generate", headers=headers, json=data).json()

for i in ['prefill', 'tokens']:
    print(f'### {i}')
    print(repr(''.join([t['text'] for t in response['details'][i]])))
```

Prints:
```
### prefill
'<s>WhatisDeepLearning?'
### tokens
'<unk><unk><unk><unk><unk><unk><unk><unk><unk><unk>'
########
```

With the change in this PR it prints:
```
### prefill
'<s>WhatisDeepLearning?'
### tokens
'\n\nDeep Learning is a subset of machine'
```

Note, using the Transformers implementation (with
`IdeficsForVisionText2Text.from_pretrained`) produces the latter
(correct) output as well.
This only happens with the 80b model, the 9b model is not as sensitive
to the dtype (as also mentioned in the code).

The reason for "forcing" this in the IDEFICS init method, is because if
quantization is used, then the dtype cannot be set explicitly. And since
it's left as `None`, it's set to `float16` by default
[here](https://github.com/huggingface/text-generation-inference/blob/96a982ad8fc232479384476b1596a880697cc1d0/server/text_generation_server/models/__init__.py#L90).
I.e. there's no other way to manually change the dtype if someone is
using quantization:
```sh
$ docker run .... ghcr.io/huggingface/text-generation-inference:latest --model-id HuggingFaceM4/idefics-80b-instruct --dtype bfloat16 --quantize bitsandbytes-nf4
.....
2023-10-31T12:42:26.710401Z  INFO shard-manager: text_generation_launcher: Starting shard rank=0
2023-10-31T12:42:30.315734Z ERROR shard-manager: text_generation_launcher: Shard complete standard error output:

Traceback (most recent call last):

  File "/opt/conda/bin/text-generation-server", line 8, in <module>
    sys.exit(app())

  File "/opt/conda/lib/python3.9/site-packages/text_generation_server/cli.py", line 80, in serve
    raise RuntimeError(

RuntimeError: Only 1 can be set between `dtype` and `quantize`, as they both decide how goes the final model.
 rank=0
Error: ShardCannotStart
2023-10-31T12:42:30.414010Z ERROR text_generation_launcher: Shard 0 failed to start
2023-10-31T12:42:30.414044Z  INFO text_generation_launcher: Shutting down shards
```

## Before submitting
- [ ] This PR fixes a typo or improves the docs (you can dismiss the
other checks if that's the case).
- [x] Did you read the [contributor
guideline](https://github.com/huggingface/transformers/blob/main/CONTRIBUTING.md#start-contributing-pull-requests),
      Pull Request section?
- [ ] Was this discussed/approved via a Github issue or the
[forum](https://discuss.huggingface.co/)? Please add a link
      to it if that's the case.
- [ ] Did you make sure to update the documentation with your changes?
Here are the
[documentation
guidelines](https://github.com/huggingface/transformers/tree/main/docs),
and
[here are tips on formatting
docstrings](https://github.com/huggingface/transformers/tree/main/docs#writing-source-documentation).
- [ ] Did you write any new necessary tests?


## Who can review?

Anyone in the community is free to review the PR once the tests have
passed. Feel free to tag
members/contributors who may be interested in your PR.

@Narsil what do you think?

<!-- Your PR will be replied to more quickly if you can figure out the
right person to tag with @


@OlivierDehaene OR @Narsil

 -->

---------

Co-authored-by: Nicolas Patry <patry.nicolas@protonmail.com>
---
 server/text_generation_server/models/idefics_causal_lm.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/server/text_generation_server/models/idefics_causal_lm.py b/server/text_generation_server/models/idefics_causal_lm.py
index 2472caf6..dcad1fa9 100644
--- a/server/text_generation_server/models/idefics_causal_lm.py
+++ b/server/text_generation_server/models/idefics_causal_lm.py
@@ -583,7 +583,7 @@ class IdeficsCausalLM(Model):
 
         if torch.cuda.is_available():
             device = torch.device("cuda")
-            dtype = torch.float16 if dtype is None else dtype
+            dtype = torch.bfloat16 if dtype is None else dtype
         else:
             if quantize:
                 raise ValueError("quantization is not available on CPU")